242 citations · 1.5k across the 60 of their papers we have counts for
13 papers · 1 filter
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Ziqian Zhong, Ziming Liu, Max Tegmark +1
Do neural networks, trained on well-understood algorithmic tasks, reliably rediscover known algorithms for solving those tasks? Several recent studies, on tasks ranging from group…
LaMPP: Language Models as Probabilistic Priors for Perception and Action
Belinda Z. Li, William Chen, Pratyusha Sharma +1
Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in cu…
Guiding Pretraining in Reinforcement Learning with Large Language Models
Yuqing Du, Olivia Watkins, Zihan Wang +5
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by…
What learning algorithm is in-context learning? Investigations with linear models
Ekin Akyürek, Dale Schuurmans, Jacob Andreas +2
Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(…
Teachable Reinforcement Learning via Advice Distillation
Olivia Watkins, Trevor Darrell, Pieter Abbeel +2
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitat…
Pre-Trained Language Models for Interactive Decision-Making
Shuang Li, Xavier Puig, Chris Paxton +11
Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an…
Skill Induction and Planning with Latent Language
Pratyusha Sharma, Antonio Torralba, Jacob Andreas
We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous de…
Leveraging Language to Learn Program Abstractions and Search Heuristics
Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum +1
Inductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, and generalizable machine learni…
Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction
Eric Chu, Deb Roy, Jacob Andreas
We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase…
Compositional Explanations of Neurons
Jesse Mu, Jacob Andreas
We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior. Compared to prior wor…
A Survey of Reinforcement Learning Informed by Natural Language
Jelena Luketina, Nantas Nardelli, Gregory Farquhar +5
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it…
Measuring Compositionality in Representation Learning
Jacob Andreas
Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or proced…
Modular Multitask Reinforcement Learning with Policy Sketches
Jacob Andreas, Dan Klein, Sergey Levine
We describe a framework for multitask deep reinforcement learning guided by policy sketches. Sketches annotate tasks with sequences of named subtasks, providing information about h…